Sequential Neural Posterior and Likelihood Approximation
This addresses simulation-based inference for researchers in statistics and machine learning, offering a more stable and efficient alternative to existing methods, though it is incremental as it builds on normalizing flows and sequential techniques.
The paper tackles inference in implicit models by introducing SNPLA, a simulation-based method that learns both the posterior and likelihood sequentially using normalizing flows, avoiding MCMC and achieving competitive performance with faster posterior draws (4 orders of magnitude).
We introduce the sequential neural posterior and likelihood approximation (SNPLA) algorithm. SNPLA is a normalizing flows-based algorithm for inference in implicit models, and therefore is a simulation-based inference method that only requires simulations from a generative model. SNPLA avoids Markov chain Monte Carlo sampling and correction-steps of the parameter proposal function that are introduced in similar methods, but that can be numerically unstable or restrictive. By utilizing the reverse KL divergence, SNPLA manages to learn both the likelihood and the posterior in a sequential manner. Over four experiments, we show that SNPLA performs competitively when utilizing the same number of model simulations as used in other methods, even though the inference problem for SNPLA is more complex due to the joint learning of posterior and likelihood function. Due to utilizing normalizing flows SNPLA generates posterior draws much faster (4 orders of magnitude) than MCMC-based methods.